physics.comp-phNov 13, 2026

Accelerating Atomistic-Continuum Simulations of Multilayer 2D Materials with Functional Principal Component Analysis-Based Machine Learning

Authors: Jonathan Oleson, Abhishek Keripale, Shashank Pathrudkar, Susanta Ghosh

Organizations: Department of Mechanical and Aerospace Engineering, Michigan Technological University, MI, USA · The Center for Artificial Intelligence at the Institute of Computing and Cybersystems, Michigan Technological University, MI, USA

Abstract

Atomistic-continuum simulations of complex wrinkling deformations in large-area multilayer two-dimensional (2D) materials are computationally expensive. To accelerate these simulations, this work presents a machine-learning (ML) framework that first constructs a low-dimensional representation of the deformation field, then learns the deformation in this reduced space. Dimensionality reduction of deformed 2D membranes is challenging because of the extremely high dimensionality of discretized deformation fields, the need to preserve surface continuity and prescribed geometric constraints, the stochastic nature of wrinkling patterns, and the limited availability of training data. We address these challenges using two-dimensional functional principal component analysis (FPCA). The proposed FPCA representation reduces deformation fields containing millions of degrees of freedom to latent spaces with only tens of dimensions while preserving the continuity of the deformed surface. In addition, prescribed homogeneous boundary constraints are satisfied exactly through an appropriate choice of basis functions in the FPCA representation. A neural network is then trained to predict the principal components from the system and loading parameters. The resulting ML-predicted deformation fields are used as high-quality initial configurations for the atomistic-continuum solver, which subsequently performs energy minimization to obtain equilibrium solutions. The framework is demonstrated for multilayer graphene subjected to uniaxial compression, biaxial compression, and combined biaxial compression and simple shear. For the most computationally intensive large-strain cases, the proposed approach achieves speedups of at least 6.8 times while converging to final energies comparable to, and in some cases lower than, those obtained using conventional atomistic-continuum initialization.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 28, 2025

ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs

Point defects play a central role in driving the properties of materials. First-principles methods are widely used to compute defect energetics and structures, including at scale for high-throughput defect databases. However, these methods are computationally expensive, making machine-learning force fields (MLFFs) an attractive alternative for accelerating structural relaxations. Most existing MLFFs are based on graph neural networks (GNNs), which can suffer from oversmoothing, oversquashing, and poor representation of long-range interactions. Both of these issues are especially of concern when modeling point defects. To address these challenges, we introduce the Accelerated Deep Atomic Potential Transformer (ADAPT), an MLFF that replaces graph representations with a direct coordinates-in-space formulation and explicitly considers all pairwise atomic interactions. Atoms are treated as tokens, with a Transformer encoder modeling their interactions. Applied to a dataset of silicon point defects, ADAPT achieves a roughly 22% reduction in force and a roughly 40 percent reduction in energy prediction error relative to a state-of-the-art GNN-based model, while requiring only a fraction of the computational cost.
Mar 29, 2026

AI-ready design of realistic 2D materials and interfaces with Mat3ra-2D

Artificial intelligence (AI) and machine learning (ML) models in materials science are predominantly trained on ideal bulk crystals, limiting their transferability to real-world applications where surfaces, interfaces, and defects dominate. We present Mat3ra-2D, an open-source framework for the rapid design of realistic two-dimensional materials and related structures, including slabs and heterogeneous interfaces, with support for disorder and defect-driven complexity. The approach combines: (1) well-defined standards for storing and exchanging materials data with a modular implementation of core concepts and (2) transformation workflows expressed as configuration-builder pipelines that preserve provenance and metadata. We implement typical structure generation tasks, such as constructing orientation-specific slabs or strain-matching interfaces, in reusable Jupyter notebooks that serve as both interactive documentation and templates for reproducible runs. To lower the barrier to adoption, we design the examples to run in any web browser and demonstrate how to incorporate these developments into a web application. Mat3ra-2D enables systematic creation and organization of realistic 2D- and interface-aware datasets for AI/ML-ready applications.
May 5, 2026

Capabilities of Auto-encoders and Principal Component Analysis of the Reduction of Microstructural Images; Application on the Acceleration of Phase-Field Simulations

In this work, a data-driven framework based on Phase-Field simulations data is proposed to highlight the capabilities of neural networks to ensure accurate low dimensionality reduction of simulated microstructural images and to provide time-series analysis. The dataset was indeed constructed from high-fidelity Phase-Field simulations. Analyses demonstrated that the association of auto-encoder neural networks and principal component analyses leads to ensure efficient and significant dimensionality reduction: 1/196 of reduction ratio with more than 80% of accuracy. These findings give insight to apply analyses on data from the latent dimension. Application of Long Short Term Memory (LSTM) neural networks showed the possibility of making next frame predictions; that makes possible the acceleration of Phase-Field simulation without the need of high computing resources. We discussed the application of such a framework on various areas of research. Different methods are proposed from the conducted analyses, in order to ensure dimensionality reduction, including auto-encoders, principal component analysis and Artificial Neural Networks, and time-series analysis, including LSTM and Gated Recurrent Unit (GRU).